HYBRINFOX at CheckThat! 2024 -- Task 1: Enhancing Language Models with Structured Information for Check-Worthiness Estimation

TL;DR

This paper presents a method that enhances language models with structured triple embeddings to improve check-worthiness estimation, showing promising results especially in English, and discusses future adaptations to larger models.

Contribution

The paper introduces a novel approach combining language models with structured triple embeddings to improve check-worthiness detection performance.

Findings

Best F1 score of 71.1 in English

Improved performance over language models alone

Mixed results in Dutch and Arabic

Abstract

This paper summarizes the experiments and results of the HYBRINFOX team for the CheckThat! 2024 - Task 1 competition. We propose an approach enriching Language Models such as RoBERTa with embeddings produced by triples (subject ; predicate ; object) extracted from the text sentences. Our analysis of the developmental data shows that this method improves the performance of Language Models alone. On the evaluation data, its best performance was in English, where it achieved an F1 score of 71.1 and ranked 12th out of 27 candidates. On the other languages (Dutch and Arabic), it obtained more mixed results. Future research tracks are identified toward adapting this processing pipeline to more recent Large Language Models.